Models / OpenBMB / MiniCPM5-2B

OpenBMB

MiniCPM5-2B

Dense 2B-class open-source model for on-device and resource-constrained use, with native long-context support, tool calling, and agentic tasks

$0.12 in · $0.74 out

per 1M tokens · provider rate closest to the median. No first-party OpenBMB price was listed. The reference price is AMD's rate, the provider closest to the median.

Context
131,072
Max output
131,072
Cache read
$0.12
Cache write
—
Reasoning
Yes
Tool calls
Yes
Structured output
Unknown
Vision
No
Open weights
Yes
License
apache-2.0
Released
Sep 6, 2026
Updated in source
Sep 12, 2026
Knowledge
—
Providers
1

Hugging Face weights

What this model costs per month

Prices are USD per 1M tokens. A month is 30 days. Cache hits use the cache-read rate when the model has one; otherwise the cache field is ignored.

monthly = requests/day × 30 × (input tokens × (1 − cache hit) × input price + input tokens × cache hit × cache-read price + output tokens × output price) ÷ 1,000,000

Providers

Base rates from Models.dev. One row per provider.
ProviderInputOutputCache readCache writeStatus
AMDreference$0.12$0.74$0.12——